© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5396
    Prev
    Next
    INDEX
    Explanations

    active followed by other words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    г
    2.00
    ী
    2.00
    ي
    1.98
    ോ
    1.71
    ্প
    1.70
    क
    1.67
    ية
    1.63
    alit
    1.59
    й
    1.58
    ків
    1.53
    POSITIVE LOGITS
    ﺍ
    1.30
     οποίο
    1.26
    wear
    1.20
    ATION
    1.20
    iją
    1.20
    ﺓ
    1.20
    ளிர்
    1.19
    »
    1.19
    یاں
    1.18
    GER
    1.17
    Activations Density 0.157%

    No Known Activations